search

microsoft / Relation-Aware-Global-Attention-Networks

We design an effective Relation-Aware Global Attention (RGA) module for CNNs to globally infer the attention.
MIT License
337 stars 65 forks source link

please look into the traceback . what could be the problem here #19

Open ssbilakeri opened 3 years ago

ssbilakeri commented 3 years ago

Traceback (most recent call last): File "train.py", line 106, in main(opt) File "train.py", line 51, in main num_classes=opt.num_classes, branch_name='rgasc') File "/content/FairMOT/src/lib/models/init.py", line 16, in create return __factory[name](*args, *kwargs) File "/content/FairMOT/src/lib/models/rga_model.py", line 112, in resnet50_rga return ResNet50_RGA_Model(args, *kwargs) File "/content/FairMOT/src/lib/models/rga_model.py", line 84, in init s_ratio=scale, c_ratio=scale, d_ratio=d_scale, model_path=model_path) File "/content/FairMOT/src/lib/models/models_utils/rga_branches.py", line 107, in init self.rga_att1 = RGA_Module(256, (height//4)(height/4), use_spatial=spa_on, use_channel=cha_on, TypeError: unsupported operand type(s) for //: 'NoneType' and 'int'